LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Meta Llama 3 70B Instruct FP8 by neuralmagic

 »  All LLMs  »  neuralmagic  »  Meta Llama 3 70B Instruct FP8   URL Share it on

  33218   
  Autotrain compatible   Conversational   En   Endpoints compatible   Fp8   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/neuralmagic/Meta-Llama-3-70B-Instruct-FP8 

Meta Llama 3 70B Instruct FP8 Benchmarks

LLME Score: 0.25423
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meta Llama 3 70B Instruct FP8 (neuralmagic/Meta-Llama-3-70B-Instruct-FP8)

Meta Llama 3 70B Instruct FP8 Parameters and Internals

Model Type 
text
Use Cases 
Areas:
commercial, research
Primary Use Cases:
assistant-like chat
Limitations:
Use in languages other than English, Use in any manner that violates applicable laws or regulations
Additional Notes 
The model uses AutoFP8 for quantization but is transitioning to llm-compressor, supporting more quantization schemes and models.
Supported Languages 
en (Fluent)
Training Details 
Methodology:
Quantization
Hardware Used:
GPU
Model Architecture:
Transformer
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Deploy with vLLM for optimized performance.
Release Notes 
Version:
1.0
Date:
6/8/2024
Notes:
Quantized to FP8 for reduced disk and memory use.
LLM NameMeta Llama 3 70B Instruct FP8
Repository 🤗https://huggingface.co/neuralmagic/Meta-Llama-3-70B-Instruct-FP8 
Model Size70b
Required VRAM72.7 GB
Updated2025-02-22
Maintainerneuralmagic
Model Typellama
Instruction-BasedYes
Model Files  4.8 GB: 1-of-15   5.0 GB: 2-of-15   4.9 GB: 3-of-15   4.9 GB: 4-of-15   4.9 GB: 5-of-15   5.0 GB: 6-of-15   4.9 GB: 7-of-15   4.9 GB: 8-of-15   4.9 GB: 9-of-15   5.0 GB: 10-of-15   4.9 GB: 11-of-15   4.9 GB: 12-of-15   4.9 GB: 13-of-15   5.0 GB: 14-of-15   3.8 GB: 15-of-15
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Meta Llama 3 70B Instruct FP8

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB40355
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB25245
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB199121
Llama3 Function Calling 1048K1024K / 141.9 GB61
...a 3 70B Instruct Gradient 524K512K / 141.9 GB23323
...a 3 70B Instruct Gradient 262K256K / 141.9 GB18655
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB3212
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB653
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB120
...a 3.1 Nemotron 70B Instruct HF128K / 141.9 GB1223352021
Note: green Score (e.g. "73.2") means that the model is better than neuralmagic/Meta-Llama-3-70B-Instruct-FP8.

Rank the Meta Llama 3 70B Instruct FP8 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 43470 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer